# FormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structure Recognition

arXiv: https://arxiv.org/abs/2608.10396 · HTML: https://mlsanity.com/paper/2608.10396/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [PubTables-1M: Towards comprehensive table extraction from unstructured documents](https://mlsanity.com/paper/2110.00061/) (2021)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [DeepSeek-OCR 2: Visual Causal Flow](https://mlsanity.com/paper/2601.20552/) (2026)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [GriTS: Grid table similarity metric for table structure recognition](https://mlsanity.com/paper/2203.12555/) (2022)
- [PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training](https://mlsanity.com/paper/2606.03264/) (2026)
- [Image2Struct: Benchmarking Structure Extraction for Vision-Language Models](https://mlsanity.com/paper/2410.22456/) (2024)
- [Multi-Modal Association based Grouping for Form Structure Extraction](https://mlsanity.com/paper/2107.04396/) (2021)
- [VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents](https://mlsanity.com/paper/2603.15118/) (2026)
- [SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding](https://mlsanity.com/paper/2406.08757/) (2024)

## Abstract (arXiv)

Transforming table-form documents into machine-processable records requires recovering not only their visible content but also the multilevel structure that organizes it. However, existing benchmarks evaluate either holistic document outputs or conventional table grids, and their aggregate scores provide little insight into where structural failures occur. We introduce FormStruct-Bench, a hierarchical and diagnostic benchmark that evaluates table-form document structure recognition at both the document level and progressively finer component levels, allowing aggregate performance to be traced back to specific structural failure modes. To construct auditable ground truth at scale, we annotate 70 reusable templates and expand them into 7,000 verified instances through a provenance-preserving Director--Artist--Verifier pipeline; all 1,100 instances in the template-disjoint test set additionally receive human review. Our evaluation protocol uses five primary metrics and three structure-specific diagnostics across page, schema, and component levels, together with slices over difficulty, structural constraints, and visual degradation. Across 14 API-hosted and locally deployable systems plus two SFT variants, the best document-level score reaches 83.85%, whereas the best reported fine-grained structural score remains below 18%. These results reveal a pronounced gap between reading document content and recovering the hierarchy and regional organization required for reliable table-form understanding.